INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.9.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.07

1:0.09

2:0.08

3:0.09

4:0.07

5:0.09

6:0.08

7:0.08

8:0.08

9:0.08

10:0.07

11:0.08

Negative Logits

 Retail

-3.92

 Household

-3.72

 Magicka

-3.25

 Collector

-3.14

 Crate

-3.14

 Attend

-3.08

 Casual

-3.02

 Catalog

-2.99

 Dealer

-2.98

 Residential

-2.94

POSITIVE LOGITS

 chimpan

2.73

ouver

2.72

ilater

2.70

nuts

2.70

 Senegal

2.65

ウス

2.65

 monkey

2.64

ierre

2.63

 Brach

2.61

Jere

2.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.